Cross-Platform Profiling and Tuning Framework for Design and Development of Heterogeneous Applications
Bibliographic record
Abstract
Parallel computing with heterogeneous platforms that include multi-core CPUs, GPGPUs, traditional GPUs and FPGAs are increasingly being employed to meet high performance demands. However, the application developer must thoroughly understand the application to parallelize tasks. It is known that careful architecture specific adjustments are required for tuning an application to effectively utilise the underlying heterogeneous devices. A cross-platform expandable profiling framework is presented that can be used to highlight bottlenecks in the application and guide design changes by providing both coarse and fine grain application statistics. Machine learning models are trained to understand the application behaviour and underlines features relating to performance. While code instrumentation is used to unlock individual code statistics of processes and kernels. The presented framework is applied to a variety of applications by profiling and tuning various benchmarks and real-life cases studies such as collision detection. Through these case studies, comparisons are made with the current industrial tools and other state of the art tuning approaches. The results highlight the unique parameters that can be extracted from the proposed framework and effectiveness of the framework due to the notable performance increase achieved.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".